© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 86804
    Prev
    Next
    INDEX
    Explanations

    include stdlib.h

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     класс
    -0.87
    頭皮
    -0.85
    vian
    -0.82
     }{@
    -0.81
    arme
    -0.79
     М
    -0.79
    }{}
    -0.77
     Ма
    -0.75
     ја
    -0.75
    URE
    -0.74
    POSITIVE LOGITS
     EXIT
    1.12
     system
    1.05
     exit
    0.98
    EXIT
    0.96
    stdlib
    0.91
    Standard
    0.90
     standard
    0.88
    system
    0.88
    exit
    0.87
    standard
    0.85
    Activations Density 0.011%

    No Known Activations